Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 2 years ago.
Improve this question
FfhggtffgtfgtgftI want develop application that whenever it recognizes a keyword it does something. it needs to be in listening mode all the time, in backgeound too.
I was exposed to this and this. I treid run it but it is not work when I am speaking.
actually I read it still doesn't support my native language. is that the reason?
I want to know how it works? does it is doing speach to text and saved it in assets files? does it is run in background? does it is used AI models? how it behaves when two apps need mic resource in parallel? noises? does it is work with Neural Networks API? how can I start developing such a thing?
thanks!
It is great you tried Vosk offline speech recognition on Android, here are some answers to your questions:
actually I read it still doesn't support my native language.
If you are about Hebrew, we might support it in the future, and you can build it yourself.
is that the reason?
You didn't provide enough information to answer this, please explain a bit more what is "it is not work"
I want to know how it works?
Extensive documentation on speech recognition is available on lectures, courses and books. You can find some introduction here for example: https://www.youtube.com/watch?v=q67z7PTGRi8
does it is doing speech to text and saved it in assets files?
It does speech to text, but it doesn't save results into assets, it just displays them. You can not modify assets, they are static.
does it is run in background?
Yes
does it is used AI models?
Sure
how it behaves when two apps need mic resource in parallel?
In android it is not possible to record audio from two apps in parallel, second one will be blocked.
noises?
It is robust to noises.
does it is work with Neural Networks API?
No, it is portable
how can I start developing such a thing?
Get some basic understanding and start writing the code. If you have further questions you can ask them in the Telegram chat
Related
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 3 years ago.
Improve this question
I am trying to create a graphical user interface (GUI) using Swing in Java.
The part I am kind of stuck is, I am planning to display some values from my Python program to the interface I am developing in Swing. I have looked up in forums and came across the Jython thing, but not quite sure on how to proceed with this, anyone information in this issue would be helpful to me.
Some extra information, if it may help, I have a set of sensors reading some values using a Raspberry Pi, and the sensors are operated using a Python script running in RPi. Now my goal is to develop a GUI using Java so that I can display those values from the Python script to the swing interface.
Thanks in advance.
I think your easiest path forward would be to store the values that are collected by the Raspberry Pi in an intermediary storage. This can be as simple as a text file, or if you want something more verbose, you can store it in a RDBMS or NoSQL DB. Then it becomes easier for the java application to look up the values without having to interface with Python.
If you want to directly interface with Python, you could look into GraalVM which has limited ability to directly execute Python code.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
I'm making a thesis about Speech Recognition for generating subtitle out of the video itself. The concept is I'm planning to make a video player and integrate the Speech Recognition on that. So if I run the system and play the video until it ends, the system will generate another copy of that video file, but this time subtitle is already included or integrated on that. Is this concept possible? If so, can you please advise me on how can I do it, or tell me whats the best SR API or some sort out there? I'm familiar in java btw.
I also had a similar sort of Idea in my mind in my university years.
I think your approach should be work. Play the Movie first time and then generate the subtitle and export it to a ".srt" file. Because you cant do it in Real-time Processing due to the several reasons like
Sentences meanings can be change from words to word
Processing or analysing time
etc.
Disadvantage of your approach is
People won't like to play the whole movie to generate the subtitle file.
So I think it would be better to extract the Sound track (audio file), analyzing the sound track and generate the Subtitle file without Playing the Movie
In here you wont able to do the SPEECH-TO-TEXT conversion.
You have to find the way to analyse the sound waves styles and extract the data.
Good Luck
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 9 years ago.
Improve this question
I'm in the early midst of making a game with Java, and would eventually like to turn it into an android application.
All the developer technical stuff aside, will the code itself remain the same, or will I have to rework the better part of it?
Thanks in advance for the feedback
Yes,you can do like that where your rendering part need to be changed if you want to use it in android. So the better option is use some framework to port your code to work in Android system as well. LibGdx is such a kind of framework where you can develop and test your application in stand alone mode and without changing your code, you can run it in Android as well. Please refer LibGDX site for more information
Android code is java, so yes!
You'll have to change some stuff. For instance, if you're using swing to show stuff on the screen, you'll have to change it to use the android API; but the core of the code should remain the same.
I remember doing my very first videogame in java. Porting it to android only required me to modify little.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 9 years ago.
Improve this question
Can you program external application from Java app.?
I know this is a wierd question but lately I really need to do it.
So the lets say I have "VLC" player or MPC or whatever it is, I want to be able to create a Java/C++ application or whatever it is to control the application such as play the video, pause the video and stuff.
If it possible please let me know and how.
It's certainly possible with VLC. Look here: http://wiki.videolan.org/Java_bindings as well as here: how to control VLC by java
For MPC, I don't know of any resources that can be used to do so. You can at least launch it to the best of my knowledge.
To start (execute) an external application you should use Runtime.getRuntime().exec(params);
or ProcessBuilder class.
http://docs.oracle.com/javase/7/docs/api/java/lang/ProcessBuilder.html
See Execute external program in java for more information.
To send key strokes to another application you could use the "Robot" class (http://docs.oracle.com/javase/6/docs/api/java/awt/Robot.html).
What is expected is to have access to interface to do these operations, you can get some references from http://caprica.github.io/vlcj/
This is java api for controlling the VLC instance embedded in AWT.
I have found this site that describes how to run external programms from java
http://www.rgagnon.com/javadetails/java-0014.html
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 2 years ago.
Improve this question
I am currently working on a project that involves the use of EEG signals on an android mobile phone.
I am deciding if I should make my own signal processing library for android or not because I can't seem to find any online.
Does anybody know of a library that I can use or would it be easier and faster to make my own?
Thanks
I'm working on a similar project. I am using the NeuroSky MindSet EEG headset and Processing IDE with the Ketai library. I could not get the NeuroSky Android API to work with either of my Android 2.3.4 or 4.0.1 phones. When digging into why it didn't work, I got lost in their API's library and decided it would probably just be easier to read the data myself. I modified the Ketai bluetooth program to read in the raw data, but did it in sort of a haphazard way (no checksum was performed). It's quite a rough hack, but I got the data to draw on the screen and have not worked on it for a couple of weeks. After I comment the code some more, I could put my code up on github - it'd be nice to get some collaboration.
By the way, if you did not intend for this to be for the Processing IDE of processing.org, you're quite lucky. As Arcymag pointed out, the keyword "processing" might trigger a response from people like myself who receive emails for processing.org. In any case, the Processing IDE has an Android mode that allows you to program Android under its IDE. If you want to develop your program in say, the Eclipse IDE, you can export your project and take all of the power of Processing with you as a library. After exporting, your code will be full Java. There are only some minor differences between Java "proper" and how Processing presents Java anyhow (some aesthetic changes). I prefer to work with the power of Processing because I am not actually a "proper" programmer, as my background is in physics, and Processing makes programming a joy. (There are several questions regarding the differences between Java proper and Processing on stackoverflow.)
This is my first post on stackoverflow. I have been looking for a way to give back since this site has saved me countless hours on this project alone. If you feel I deserve an upvote, you'd make one noob very happy. I can do things such as: post more than two hyperlinks and upvote answers.